EXPERT Causal Agent
WHITE-BOX LLM / VLM
Causal Driven World Model
Causal Discovery Model
© 2025 Abel.AI, Inc. All rights reserved.
Office San Francisco
X →
linkedin →
CONTACT hi@abel.ai
Advancing the frontier of causal intelligence - by develop foundation models and agents that reason not only from patterns, but from cause-and-effect. Unlike large language models (LLMs) that rely on next-token prediction without explicit causal structure, our systems are designed to be interpretable, generalizable, and intervention-ready.
Pioneering Causality-Empowered Models
for the Next Generation of Intelligence
/ Research /
Research Directions
Why Causality Matters
While today’s LLMs excel at fluency and pattern recognition,
they face critical limitations
Limited
Interpretability
Weak Generalization
No Interventions or Counterfactuals
Coherent outputs without structured causal representations.
Fragile under out-of-distribution shifts.
Incapable of systematic “what-if” reasoning for decision support.
Research pioneers pillars of causality-empowered AI
Related Paper List
Research Topics
Research Topics
Related Paper List
"Towards generalizable reinforcement learning via causality-guided self-adaptive representations." Yang, Yupei, Biwei Huang, Fan Feng, Xinyue Wang, Shikui Tu, and Lei Xu. arXiv preprint arXiv:2407.20651 (2024).
"Modeling Unseen Environments with Language-guided Composable Causal Components in Reinforcement Learning." Wang, Xinyue, and Biwei Huang. arXiv preprint arXiv:2505.08361 (2025).
"Learning world models with identifiable factorization." Liu, Yuren, Biwei Huang, Zhengmao Zhu, Honglong Tian, Mingming Gong, Yang Yu, and Kun Zhang. Advances in Neural Information Processing Systems 36 (2023): 31831-31864.
03｜Causal Driven World Model
05｜Counterfactual Reasoning
"Natural counterfactuals with necessary backtracking." Hao, Guang-Yuan, Jiji Zhang, Biwei Huang, Hao Wang, and Kun Zhang. Advances in Neural Information Processing Systems 37 (2024): 14962-14995.
"Counterfactual generation with identifiability guarantees." Yan, Hanqi, Lingjing Kong, Lin Gui, Yuejie Chi, Eric Xing, Yulan He, and Kun Zhang. Advances in Neural Information Processing Systems 36 (2023): 56256-56277.
These innovations strengthen the foundations
of intelligence systems across domains.